The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which creates a surface for indirect prompt injection attacks.
Ingestion points: The Python examples in SKILL.md demonstrate reading data from local files like quarterly_sales.csv and global_sales.csv using the pandas library.
Boundary markers: There are no instructions or delimiters provided to ensure the agent ignores or isolates instructions that might be embedded within these data files.
Capability inventory: The skill includes capabilities to write to the file system through matplotlib.pyplot.savefig and plotly.graph_objects.Figure.write_html.
Sanitization: The skill does not implement any validation, filtering, or sanitization of the content read from external files before processing it for visualization.

data-visualization